diff --git a/src/transformers/__init__.py b/src/transformers/__init__.py
index 1d6d43765d..fe007017d0 100755
--- a/src/transformers/__init__.py
+++ b/src/transformers/__init__.py
@@ -31,6 +31,7 @@ from .configuration_openai import OPENAI_GPT_PRETRAINED_CONFIG_ARCHIVE_MAP, Open
 from .configuration_roberta import ROBERTA_PRETRAINED_CONFIG_ARCHIVE_MAP, RobertaConfig
 from .configuration_t5 import T5_PRETRAINED_CONFIG_ARCHIVE_MAP, T5Config
 from .configuration_transfo_xl import TRANSFO_XL_PRETRAINED_CONFIG_ARCHIVE_MAP, TransfoXLConfig
+
 # Configurations
 from .configuration_utils import PretrainedConfig
 from .configuration_xlm import XLM_PRETRAINED_CONFIG_ARCHIVE_MAP, XLMConfig
@@ -55,6 +56,7 @@ from .data import (
     xnli_processors,
     xnli_tasks_num_labels,
 )
+
 # Files and general utilities
 from .file_utils import (
     CONFIG_NAME,
@@ -71,8 +73,10 @@ from .file_utils import (
     is_tf_available,
     is_torch_available,
 )
+
 # Model Cards
 from .modelcard import ModelCard
+
 # TF 2.0 <=> PyTorch conversion utilities
 from .modeling_tf_pytorch_utils import (
     convert_tf_weight_name_to_pt_weight_name,
@@ -83,6 +87,7 @@ from .modeling_tf_pytorch_utils import (
     load_tf2_model_in_pytorch_model,
     load_tf2_weights_in_pytorch_model,
 )
+
 # Pipelines
 from .pipelines import (
     CsvPipelineDataFormat,
@@ -108,6 +113,7 @@ from .tokenization_openai import OpenAIGPTTokenizer
 from .tokenization_roberta import RobertaTokenizer
 from .tokenization_t5 import T5Tokenizer
 from .tokenization_transfo_xl import TransfoXLCorpus, TransfoXLTokenizer
+
 # Tokenizers
 from .tokenization_utils import PreTrainedTokenizer
 from .tokenization_xlm import XLMTokenizer
@@ -377,7 +383,12 @@ if is_tf_available():
         TF_ALBERT_PRETRAINED_MODEL_ARCHIVE_MAP,
     )
 
-    from .modeling_tf_t5 import TFT5PreTrainedModel, TFT5Model, TFT5WithLMHeadModel, TF_T5_PRETRAINED_MODEL_ARCHIVE_MAP
+    from .modeling_tf_t5 import (
+        TFT5PreTrainedModel,
+        TFT5Model,
+        TFT5WithLMHeadModel,
+        TF_T5_PRETRAINED_MODEL_ARCHIVE_MAP,
+    )
 
     # Optimization
     from .optimization_tf import WarmUp, create_optimizer, AdamWeightDecay, GradientAccumulator
diff --git a/src/transformers/convert_pytorch_checkpoint_to_tf2.py b/src/transformers/convert_pytorch_checkpoint_to_tf2.py
index a4be629257..cdc0c7bd18 100644
--- a/src/transformers/convert_pytorch_checkpoint_to_tf2.py
+++ b/src/transformers/convert_pytorch_checkpoint_to_tf2.py
@@ -54,7 +54,6 @@ from transformers import (
     TFT5WithLMHeadModel,
     TFTransfoXLLMHeadModel,
     TFXLMRobertaForMaskedLM,
-    TFXLMRobertaForSequenceClassification,
     TFXLMWithLMHeadModel,
     TFXLNetLMHeadModel,
     TransfoXLConfig,
@@ -266,13 +265,6 @@ MODEL_CLASSES = {
         DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP,
         DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
     ),
-    "distilbert-base-uncased-distilled-squad": (
-        DistilBertConfig,
-        TFDistilBertForQuestionAnswering,
-        DistilBertForQuestionAnswering,
-        DISTILBERT_PRETRAINED_MODEL_ARCHIVE_MAP,
-        DISTILBERT_PRETRAINED_CONFIG_ARCHIVE_MAP,
-    ),
     "ctrl": (
         CTRLConfig,
         TFCTRLLMHeadModel,
diff --git a/templates/adding_a_new_example_script/run_xxx.py b/templates/adding_a_new_example_script/run_xxx.py
index 448c59aadb..77d9ae4c7c 100644
--- a/templates/adding_a_new_example_script/run_xxx.py
+++ b/templates/adding_a_new_example_script/run_xxx.py
@@ -52,6 +52,7 @@ from utils_squad import (
     write_predictions,
     write_predictions_extended,
 )
+
 # The follwing import is the official SQuAD evaluation script (2.0).
 # You can remove it from the dependencies if you are using this script outside of the library
 # We've added it here for automated tests (see examples/test_examples.py file)
diff --git a/templates/adding_a_new_example_script/utils_xxx.py b/templates/adding_a_new_example_script/utils_xxx.py
index 172a1b03a2..b8f8cdf2b9 100644
--- a/templates/adding_a_new_example_script/utils_xxx.py
+++ b/templates/adding_a_new_example_script/utils_xxx.py
@@ -21,6 +21,7 @@ import logging
 import math
 
 from transformers.tokenization_bert import BasicTokenizer, whitespace_tokenize
+
 # Required by XLNet evaluation method to compute optimal threshold (see write_predictions_extended() method)
 from utils_squad_evaluate import find_all_best_thresh_v2, get_raw_scores, make_qid_to_has_ans